# Unsupervised representation learning with recognition-parametrised probabilistic models

arXiv: https://arxiv.org/abs/2209.05661 · HTML: https://mlsanity.com/paper/2209.05661/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 44 references that are in the map.
- First posted on arXiv 13 Sep 2022.

## Builds on (most cited first, 16 of 16)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Variational Inference with Normalizing Flows](https://mlsanity.com/paper/1505.05770/) (2015)
- [Variational Diffusion Models](https://mlsanity.com/paper/2107.00630/) (2021)
- [The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables](https://mlsanity.com/paper/1611.00712/) (2016)
- [Importance Weighted Autoencoders](https://mlsanity.com/paper/1509.00519/) (2015)
- [Unity: A General Platform for Intelligent Agents](https://mlsanity.com/paper/1809.02627/) (2018)
- [Composing graphical models with neural networks for structured representations and fast inference](https://mlsanity.com/paper/1603.06277/) (2016)
- [Filtering Variational Objectives](https://mlsanity.com/paper/1705.09279/) (2017)
- [The Thermodynamic Variational Objective](https://mlsanity.com/paper/1907.00031/) (2019)
- [Sparse Gaussian Process Variational Autoencoders](https://mlsanity.com/paper/2010.10177/) (2020)
- [A neurally plausible model learns successor representations in partially observable environments](https://mlsanity.com/paper/1906.09480/) (2019)
- [Flexible and accurate inference and learning for deep generative models](https://mlsanity.com/paper/1805.11051/) (2018)
- [Amortised Learning by Wake-Sleep](https://mlsanity.com/paper/2002.09737/) (2020)

## Built on by (most cited first, 5 of 5)

- [Understanding Self-Supervised Learning via Latent Distribution Matching](https://mlsanity.com/paper/2605.03517/) (2026)
- [Maximum Likelihood Learning of Latent Dynamics Without Reconstruction](https://mlsanity.com/paper/2505.23569/) (2025)
- [Probabilistic Variational Contrastive Learning](https://mlsanity.com/paper/2506.10159/) (2025)
- [Prediction under Latent Subgroup Shifts with High-Dimensional Observations](https://mlsanity.com/paper/2306.13472/) (2023)
- [RAMP: Recognition parametrisation by Amortised Message Passing](https://mlsanity.com/paper/2607.18883/) (2026)

## Abstract (arXiv)

We introduce a new approach to probabilistic unsupervised learning based on the recognition-parametrised model (RPM): a normalised semi-parametric hypothesis class for joint distributions over observed and latent variables. Under the key assumption that observations are conditionally independent given latents, the RPM combines parametric prior and observation-conditioned latent distributions with non-parametric observation marginals. This approach leads to a flexible learnt recognition model capturing latent dependence between observations, without the need for an explicit, parametric generative model. The RPM admits exact maximum-likelihood learning for discrete latents, even for powerful neural-network-based recognition. We develop effective approximations applicable in the continuous-latent case. Experiments demonstrate the effectiveness of the RPM on high-dimensional data, learning image classification from weak indirect supervision; direct image-level latent Dirichlet allocation; and recognition-parametrised Gaussian process factor analysis (RP-GPFA) applied to multi-factorial spatiotemporal datasets. The RPM provides a powerful framework to discover meaningful latent structure underlying observational data, a function critical to both animal and artificial intelligence.